Predicting Defective Engines using Convolutional Neural Networks on Temporal Vibration Signals

Nikou Günnemann, Jürgen Pfeffer
Proceedings of the First International Workshop on Learning with Imbalanced Domains: Theory and Applications, PMLR 74:92-102, 2017.

Abstract

This paper addresses for the first time the problem of engines’ damage prediction using huge amounts of imbalanced data from "structure borne noise" signals related to the internal engine excitation. We propose the usage of a convolutional neural network on our temporal input signals, subsequently combined with additional static features. Using informative mini batches during training we take the imbalance of the data into account. The experimental results indicate good performance in detecting the minority class on our large real-world use case.

Cite this Paper

BibTeX
@InProceedings{pmlr-v74-günnemann17a, title = {Predicting Defective Engines using Convolutional Neural Networks on Temporal Vibration Signals}, author = {Günnemann, Nikou and Pfeffer, Jürgen}, booktitle = {Proceedings of the First International Workshop on Learning with Imbalanced Domains: Theory and Applications}, pages = {92--102}, year = {2017}, editor = {Luís Torgo, Paula Branco and Moniz, Nuno}, volume = {74}, series = {Proceedings of Machine Learning Research}, month = {22 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v74/günnemann17a/günnemann17a.pdf}, url = {https://proceedings.mlr.press/v74/g%C3%BCnnemann17a.html}, abstract = {This paper addresses for the first time the problem of engines’ damage prediction using huge amounts of imbalanced data from "structure borne noise" signals related to the internal engine excitation. We propose the usage of a convolutional neural network on our temporal input signals, subsequently combined with additional static features. Using informative mini batches during training we take the imbalance of the data into account. The experimental results indicate good performance in detecting the minority class on our large real-world use case.} }
Endnote
%0 Conference Paper %T Predicting Defective Engines using Convolutional Neural Networks on Temporal Vibration Signals %A Nikou Günnemann %A Jürgen Pfeffer %B Proceedings of the First International Workshop on Learning with Imbalanced Domains: Theory and Applications %C Proceedings of Machine Learning Research %D 2017 %E Paula Branco Luís Torgo %E Nuno Moniz %F pmlr-v74-günnemann17a %I PMLR %P 92--102 %U https://proceedings.mlr.press/v74/g%C3%BCnnemann17a.html %V 74 %X This paper addresses for the first time the problem of engines’ damage prediction using huge amounts of imbalanced data from "structure borne noise" signals related to the internal engine excitation. We propose the usage of a convolutional neural network on our temporal input signals, subsequently combined with additional static features. Using informative mini batches during training we take the imbalance of the data into account. The experimental results indicate good performance in detecting the minority class on our large real-world use case.
APA
Günnemann, N. & Pfeffer, J.. (2017). Predicting Defective Engines using Convolutional Neural Networks on Temporal Vibration Signals. Proceedings of the First International Workshop on Learning with Imbalanced Domains: Theory and Applications, in Proceedings of Machine Learning Research 74:92-102 Available from https://proceedings.mlr.press/v74/g%C3%BCnnemann17a.html.

Related Material